Monitoring Downhole Machinery Operations Using Noncontact Triboelectric Nanogenerators and Deep Learning

Accurate monitoring of downhole equipment during drilling processes holds significant importance in mitigating drilling risks and accidents while enhancing drilling efficiency. Instantaneous reversal and lateral vibrations of downhole machinery can cause substantial damage to the equipment and drill bit, making them crucial parameters to monitor. This article proposes a noncontact triboelectric nanogenerator (NC-TENG) capable of employing deep learning methods to monitor four operational conditions in downhole environments: clockwise rotation, counterclockwise rotation, low-frequency vibration interference, and high-frequency vibration interference, achieving a classification accuracy of up to 99.45%. Furthermore, the NC-TENG boasts advantages such as a simple structure, extended lifespan, and high signal-to-noise ratio, making it more suitable for complex downhole conditions. The introduction of the NC-TENG offers a viable approach for the development of novel intelligent measurement devices and technologies for downhole applications.